hw/loongarch: Add numa support

1. Implement some functions for LoongArch numa support;
2. Implement fdt_add_memory_node() for fdt;
3. build_srat() fills node_id and adds build numa memory.

Reviewed-by: Song Gao <gaosong@loongson.cn>
Signed-off-by: Tianrui Zhao <zhaotianrui@loongson.cn>
Signed-off-by: Song Gao <gaosong@loongson.cn>
Message-Id: <20230613122613.2471743-1-zhaotianrui@loongson.cn>

1 files changed, 90 insertions, 12 deletions

diff --git a/hw/loongarch/virt.c b/hw/loongarch/virt.c
index 17bc37bccd..1d5c764408 100644
--- a/hw/loongarch/virt.c
+++ b/hw/loongarch/virt.c
@@ -164,11 +164,16 @@ static void fdt_add_cpu_nodes(const LoongArchMachineState *lams)
     for (num = smp_cpus - 1; num >= 0; num--) {
         char *nodename = g_strdup_printf("/cpus/cpu@%d", num);
         LoongArchCPU *cpu = LOONGARCH_CPU(qemu_get_cpu(num));
+        CPUState *cs = CPU(cpu);
 
         qemu_fdt_add_subnode(ms->fdt, nodename);
         qemu_fdt_setprop_string(ms->fdt, nodename, "device_type", "cpu");
         qemu_fdt_setprop_string(ms->fdt, nodename, "compatible",
                                 cpu->dtb_compatible);
+        if (ms->possible_cpus->cpus[cs->cpu_index].props.has_node_id) {
+            qemu_fdt_setprop_cell(ms->fdt, nodename, "numa-node-id",
+                ms->possible_cpus->cpus[cs->cpu_index].props.node_id);
+        }
         qemu_fdt_setprop_cell(ms->fdt, nodename, "reg", num);
         qemu_fdt_setprop_cell(ms->fdt, nodename, "phandle",
                               qemu_fdt_alloc_phandle(ms->fdt));
@@ -280,6 +285,22 @@ static void fdt_add_irqchip_node(LoongArchMachineState *lams)
     g_free(nodename);
 }
 
+static void fdt_add_memory_node(MachineState *ms,
+                                uint64_t base, uint64_t size, int node_id)
+{
+    char *nodename = g_strdup_printf("/memory@%" PRIx64, base);
+
+    qemu_fdt_add_subnode(ms->fdt, nodename);
+    qemu_fdt_setprop_cells(ms->fdt, nodename, "reg", 2, base, 2, size);
+    qemu_fdt_setprop_string(ms->fdt, nodename, "device_type", "memory");
+
+    if (ms->numa_state && ms->numa_state->num_nodes) {
+        qemu_fdt_setprop_cell(ms->fdt, nodename, "numa-node-id", node_id);
+    }
+
+    g_free(nodename);
+}
+
 #define PM_BASE 0x10080000
 #define PM_SIZE 0x100
 #define PM_CTRL 0x10
@@ -767,14 +788,17 @@ static void loongarch_init(MachineState *machine)
     const char *cpu_model = machine->cpu_type;
     ram_addr_t offset = 0;
     ram_addr_t ram_size = machine->ram_size;
-    uint64_t highram_size = 0;
+    uint64_t highram_size = 0, phyAddr = 0;
     MemoryRegion *address_space_mem = get_system_memory();
     LoongArchMachineState *lams = LOONGARCH_MACHINE(machine);
+    int nb_numa_nodes = machine->numa_state->num_nodes;
+    NodeInfo *numa_info = machine->numa_state->nodes;
     int i;
     hwaddr fdt_base;
     const CPUArchIdList *possible_cpus;
     MachineClass *mc = MACHINE_GET_CLASS(machine);
     CPUState *cpu;
+    char *ramName = NULL;
 
     if (!cpu_model) {
         cpu_model = LOONGARCH_CPU_TYPE_NAME("la464");
@@ -799,17 +823,43 @@ static void loongarch_init(MachineState *machine)
         machine->possible_cpus->cpus[i].cpu = OBJECT(cpu);
     }
     fdt_add_cpu_nodes(lams);
-    /* Add memory region */
-    memory_region_init_alias(&lams->lowmem, NULL, "loongarch.lowram",
-                             machine->ram, 0, 256 * MiB);
-    memory_region_add_subregion(address_space_mem, offset, &lams->lowmem);
-    offset += 256 * MiB;
-    memmap_add_entry(0, 256 * MiB, 1);
-    highram_size = ram_size - 256 * MiB;
-    memory_region_init_alias(&lams->highmem, NULL, "loongarch.highmem",
-                             machine->ram, offset, highram_size);
-    memory_region_add_subregion(address_space_mem, 0x90000000, &lams->highmem);
-    memmap_add_entry(0x90000000, highram_size, 1);
+
+    /* Node0 memory */
+    memmap_add_entry(VIRT_LOWMEM_BASE, VIRT_LOWMEM_SIZE, 1);
+    fdt_add_memory_node(machine, VIRT_LOWMEM_BASE, VIRT_LOWMEM_SIZE, 0);
+    memory_region_init_alias(&lams->lowmem, NULL, "loongarch.node0.lowram",
+                             machine->ram, offset, VIRT_LOWMEM_SIZE);
+    memory_region_add_subregion(address_space_mem, phyAddr, &lams->lowmem);
+
+    offset += VIRT_LOWMEM_SIZE;
+    if (nb_numa_nodes > 0) {
+        assert(numa_info[0].node_mem > VIRT_LOWMEM_SIZE);
+        highram_size = numa_info[0].node_mem - VIRT_LOWMEM_SIZE;
+    } else {
+        highram_size = ram_size - VIRT_LOWMEM_SIZE;
+    }
+    phyAddr = VIRT_HIGHMEM_BASE;
+    memmap_add_entry(phyAddr, highram_size, 1);
+    fdt_add_memory_node(machine, phyAddr, highram_size, 0);
+    memory_region_init_alias(&lams->highmem, NULL, "loongarch.node0.highram",
+                              machine->ram, offset, highram_size);
+    memory_region_add_subregion(address_space_mem, phyAddr, &lams->highmem);
+
+    /* Node1 - Nodemax memory */
+    offset += highram_size;
+    phyAddr += highram_size;
+
+    for (i = 1; i < nb_numa_nodes; i++) {
+        MemoryRegion *nodemem = g_new(MemoryRegion, 1);
+        ramName = g_strdup_printf("loongarch.node%d.ram", i);
+        memory_region_init_alias(nodemem, NULL, ramName, machine->ram,
+                                 offset,  numa_info[i].node_mem);
+        memory_region_add_subregion(address_space_mem, phyAddr, nodemem);
+        memmap_add_entry(phyAddr, numa_info[i].node_mem, 1);
+        fdt_add_memory_node(machine, phyAddr, numa_info[i].node_mem, i);
+        offset += numa_info[i].node_mem;
+        phyAddr += numa_info[i].node_mem;
+    }
 
     /* initialize device memory address space */
     if (machine->ram_size < machine->maxram_size) {
@@ -1052,6 +1102,29 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms)
     return ms->possible_cpus;
 }
 
+static CpuInstanceProperties
+virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index)
+{
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
+    const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(ms);
+
+    assert(cpu_index < possible_cpus->len);
+    return possible_cpus->cpus[cpu_index].props;
+}
+
+static int64_t virt_get_default_cpu_node_id(const MachineState *ms, int idx)
+{
+    int64_t nidx = 0;
+
+    if (ms->numa_state->num_nodes) {
+        nidx = idx / (ms->smp.cpus / ms->numa_state->num_nodes);
+        if (ms->numa_state->num_nodes <= nidx) {
+            nidx = ms->numa_state->num_nodes - 1;
+        }
+    }
+    return nidx;
+}
+
 static void loongarch_class_init(ObjectClass *oc, void *data)
 {
     MachineClass *mc = MACHINE_CLASS(oc);
@@ -1069,6 +1142,11 @@ static void loongarch_class_init(ObjectClass *oc, void *data)
     mc->default_boot_order = "c";
     mc->no_cdrom = 1;
     mc->possible_cpu_arch_ids = virt_possible_cpu_arch_ids;
+    mc->cpu_index_to_instance_props = virt_cpu_index_to_props;
+    mc->get_default_cpu_node_id = virt_get_default_cpu_node_id;
+    mc->numa_mem_supported = true;
+    mc->auto_enable_numa_with_memhp = true;
+    mc->auto_enable_numa_with_memdev = true;
     mc->get_hotplug_handler = virt_machine_get_hotplug_handler;
     mc->default_nic = "virtio-net-pci";
     hc->plug = loongarch_machine_device_plug_cb;